在药物发现中，表型（Phenotypic） 通常指的是细胞或生物体在药物处理后所表现出的可观察特征或变化。这些变化可以包括细胞形态、基因表达、蛋白质水平和代谢产物等多种生物学响应。
在表型药物发现（Phenotypic Drug Discovery, PDD） 中，研究人员通过观察和分析这些表型变化来评估药物的效果和潜在的治疗机制。
In drug discovery, phenotypic typically refers to the observable characteristics or changes in cells or organisms after drug treatment. These changes can include various biological responses such as cell morphology, gene expression, protein levels, and metabolites.
In Phenotypic Drug Discovery (PDD), researchers evaluate the effects and potential therapeutic mechanisms of drugs by observing and analyzing these phenotypic changes.
Considering the increasing number of papers in this field, we roughly summarize some articles and put them into the following categories:
- [2024] Morphological profiling for drug discovery in the era of deep learning (Briefings in Bioinformatics) [paper] [中文解读]
- [2024] Artificial intelligence for high content imaging in drug discovery (Current Opinion in Structural Biology) [paper]
- [2023] Deep learning in image-based phenotypic drug discovery (Trends in Cell Biology) [paper]
- [2022] Phenotypic drug discovery: recent successes, lessons learned and new directions (Nature Reviews Drug Discovery) [paper]
- [2020] Image-based profiling for drug discovery: due for a machine-learning upgrade? (Nature Reviews Drug Discovery) [paper]
- [Board Cell Painting Gallery] [Link] [Datasets Overview] [AWS Overview] [Bray Dataset]
- [Broad Bioimage Benchmark Collection] [Link] [Paper]
- [Image Data Resource (IDR)] [Link]
- [NYSCF Automated Deep Phenotyping Dataset (ADPD)] [Link]
- [DeepProfiler] Learning representations for image-based profiling of perturbations (Nature Communications) [paper] [code]
- [Pycytominer] Reproducible image-based profiling with Pycytominer (Arxiv) [paper] [code]
- [CellProfiler] CellProfiler 3.0:Next-generation imageprocessing for biology (PLOS BIOLOGY) [paper] [code]
- [CellSAM] CellSAM: A Foundation Model for Cell Segmentation (Biorxiv) [paper] [code]
- [Cellpose] Cellpose: a generalist algorithm for cellular segmentation (Nature Methods) [paper] [code]
Details
-
[PhenoScreen] PhenoScreen: A Dual-Space Contrastive Learning Framework-based Phenotypic Screening Method by Linking Chemical Perturbations to Cellular Morphology (BioRxiv) [paper] [code]
-
[Batch Correction] Evaluating batch correction methods for image-based cell profiling (Nature Communications) [paper] [code]
-
[scDINO] Self-supervised vision transformers accurately decode cellular state heterogeneity (BioRxiv) [paper][code]
-
[MIGA] Cross-Modal Graph Contrastive Learning with Cellular Images (Advanced science) [paper] [code]
-
Deep representation learning determines drug mechanism of action from cell painting images (Digital Discovery) [paper] [code]
-
[CLOOME(NC)] CLOOME: contrastive learning unlocks bioimaging databases for queries with chemical structures (Nature Communications) [paper] [code]
-
[Dataset] Integrating deep learning and unbiased automated high-content screening to identify complex disease signatures in human fibroblasts (Nature Communications) [paper] [dataset]
-
[WS-DINO] Self-Supervised Learning of Phenotypic Representations from Cell Images with Weak Labels (LMRL @NeurIPS 2022) [paper] [code]
-
[CLOOME] Contrastive learning of image- and structure-based representations in drug discovery (MLDD @ICLR 2022) [paper] [code]
[文章解读]
Details
-
[PRnet] Predicting transcriptional responses to novel chemical perturbations using deep generative model for drug discovery (Nature Communications) [paper] [code]
-
[PertKGE] Identifying compound-protein interactions with knowledge graph embedding of perturbation transcriptomics (Cell Genomics) [paper] [code]
-
An interpretable deep learning framework for genome-informed precision oncology (Nature Machine Intelligence) [paper] [code]
-
[PERCEPTION] PERCEPTION predicts patient response and resistance to treatment using single-cell transcriptomics of their tumors (Nature Cancer) [paper] [code]
-
[SCAD] Enabling Single-Cell Drug Response Annotations from Bulk RNA-Seq Using SCAD (Advanced Science) [paper] [code]
-
[ASGARD] ASGARD is A Single-cell Guided Pipeline to Aid Repurposing of Drugs (Nature Communications) [paper] [code]
-
[scDEAL] Deep transfer learning of cancer drug responses by integrating bulk and single-cell RNA-seq data (Nature Communications) [paper] [code]
-
[chemCPA] Predicting Cellular Responses to Novel Drug Perturbations at a Single-Cell Resolution (NIPS 2022) [paper] [code]
-
[Velodrome] Out-of-distribution generalization from labelled and unlabelled gene expression data for drug response prediction (Nature Machine Intelligence) [paper] [code]
-
[PathDSP] Explainable drug sensitivity prediction through cancer pathway enrichment (Scientific reports) [paper] [code]
-
[VAEN] Deep generative neural network for accurate drug response imputatio (Nature Communications) [paper] [code]
Details
-
[Datasets] JUMP Cell Painting dataset: morphological impact of 136,000 chemical and genetic perturbations (Arxiv) [paper] [dataset]
-
Cell morphological representations of genes enhance prediction of drug targets (Biorxiv) [paper]
-
[Datasets and Benchmark] Three million images and morphological profiles of cells treated with matched chemical and genetic perturbations (Nature Methods) [paper] [code]
-
[cmQTL] High-dimensional phenotyping to define the genetic basis of cellular morphology (Nature Communications) [paper] [code]
-
[InfoAlign] Learning Molecular Representation in a Cell (Arxiv) [paper] [code]
-
[InfoCORE] Removing Biases from Molecular Representations via Information Maximization (ICLR) [paper] [code]
-
Predicting compound activity from phenotypic profiles and chemical structures (Nature Communications) [paper] [code]
-
[Multimodal deep learning] Pan-Cancer Integrative Histology-Genomic Analysis via Multimodal Deep Learning (Cancer Cell) [paper] [code]
-
[Datasets and Benchmark] High-dimensional gene expression and morphology profiles of cells across 28,000 genetic and chemical perturbations (Nature Methods) [paper] [code]
-
Morphology and gene expression profiling provide complementary information for mapping cell state (Cell Systems) [paper] [code]
-
Integrating cell morphology with gene expression and chemical structure to aid mitochondrial toxicity detection (Communications Biology) [paper] [code]
Details
-
[ChannelViT] Channel Vision Transformer: An Image Is Worth C x 16 x 16 Words (ICLR 2024) [paper] [code]
-
[CHAMMI] CHAMMI: A benchmark for channel-adaptive models in microscopy imaging (NIPS 2024) [paper] [code]
-
[DiChaViT] Enhancing Feature Diversity Boosts Channel-Adaptive Vision Transformers (ArxiV) [paper]
-
[ChAda-ViT] ChAda-ViT : Channel Adaptive Attention for Joint Representation Learning of Heterogeneous Microscopy Images (CVPR 2024) [paper] [code]
